Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression over time

    oai_token-act-pair · gpt-3.5-turbo

    actions or states that build up over time or improve progressively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppers
    -0.74
    ools
    -0.71
    ogun
    -0.65
    ouch
    -0.65
    assad
    -0.62
    shut
    -0.61
    ãĤ®
    -0.61
    umbn
    -0.61
    Ò
    -0.60
    perse
    -0.60
    POSITIVE LOGITS
     progresses
    1.02
     progressively
    0.98
     evolves
    0.91
     progressed
    0.87
     increasing
    0.86
     veter
    0.85
     grows
    0.84
     decreasing
    0.84
     increments
    0.82
     increases
    0.82
    Act Density 0.398%

    No Known Activations